AI agents call get_pipeline_graph to retrieve information from Gst without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and renders information about an existing GStreamer pipeline in DOT format for visualization purposes. It has no side effects on the pipeline, does not create or modify pipeline state, and does not execute arbitrary code or commands. It is purely informational, matching the 'Read' category which covers retrieval and querying operations.
From the tool's definition The tool 'get_pipeline_graph' generates a DOT graph representation of a GStreamer pipeline. The verb 'generate' combined with 'graph representation' indicates data retrieval and visualization, not modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Generate a DOT graph representation of a GStreamer pipeline. It is categorised as a Read tool in the Gst MCP Server, which means it retrieves data without modifying state.
Register the Gst MCP server in PolicyLayer and add a rule for get_pipeline_graph: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gst. Nothing to install.
get_pipeline_graph is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_pipeline_graph rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_pipeline_graph. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_pipeline_graph is provided by the Gst MCP server (wizenink/gst-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →